An Embedded Diachronic Sense Change Model with a Case Study from Ancient Greek
This work addresses the challenge of accurately tracking sense evolution in historical linguistics, particularly for ancient Greek, but it is incremental as it builds on prior models like DiSC.
The paper tackled the problem of modeling word sense change in ancient languages with small, sparse corpora by introducing EDiSC, an embedded diachronic sense change model that combines word embeddings with an existing generative model, resulting in improved predictive accuracy, ground-truth recovery, uncertainty quantification, sampling efficiency, and scalability.
Word meanings change over time, and word senses evolve, emerge or die out in the process. For ancient languages, where the corpora are often small and sparse, modelling such changes accurately proves challenging, and quantifying uncertainty in sense-change estimates consequently becomes important. GASC (Genre-Aware Semantic Change) and DiSC (Diachronic Sense Change) are existing generative models that have been used to analyse sense change for target words from an ancient Greek text corpus, using unsupervised learning without the help of any pre-training. These models represent the senses of a given target word such as "kosmos" (meaning decoration, order or world) as distributions over context words, and sense prevalence as a distribution over senses. The models are fitted using Markov Chain Monte Carlo (MCMC) methods to measure temporal changes in these representations. This paper introduces EDiSC, an Embedded DiSC model, which combines word embeddings with DiSC to provide superior model performance. It is shown empirically that EDiSC offers improved predictive accuracy, ground-truth recovery and uncertainty quantification, as well as better sampling efficiency and scalability properties with MCMC methods. The challenges of fitting these models are also discussed.